	Claude Haiku 4.5	Gemini 2.5 Flash	Gemma 3 12b It	GPT 4.1 Mini	GPT 4.1 Nano	GPT 4o Mini
Score	2nd 81.5%	1st 81.5%	6th 71.4%	3rd 77.7%	5th 73.1%	4th 74.5%
58.3%	67%	56%	62%	57%	58%	50%
79.2%	85%	71%	74%	80%	73%	92%
75.3%	88%	84%	67%	76%	72%	65%
74.2%	76%	77%	77%	78%	67%	70%
83.2%	84%	88%	81%	70%	82%	94%
80.8%	83%	83%	78%	78%	81%	82%
87.7%	95%	92%	80%	91%	85%	83%
60.5%	77%	95%	47%	38%	61%	45%
62.3%	61%	72%	51%	73%	64%	53%
77.7%	82%	82%	68%	74%	78%	82%
93.0%	88%	98%	91%	92%	94%	95%
91.7%	91%	91%	90%	90%	93%	95%
43.0%	65%	59%	10%	51%	44%	29%
85.5%	87%	89%	76%	90%	81%	90%
84.2%	94%	84%	77%	84%	83%	83%
83.7%	89%	87%	73%	84%	75%	94%
75.8%	80%	82%	67%	81%	74%	71%
72.7%	76%	84%	62%	76%	73%	65%
70.2%	82%	79%	68%	76%	50%	66%
66.3%	69%	73%	51%	66%	77%	62%
84.0%	85%	90%	72%	88%	81%	88%
84.5%	96%	93%	69%	86%	83%	80%
48.2%	49%	60%	53%	41%	45%	41%
79.0%	87%	84%	71%	79%	75%	78%
80.0%	83%	87%	78%	84%	66%	82%
85.3%	94%	93%	82%	93%	66%	84%
91.0%	95%	87%	90%	93%	93%	88%
71.5%	81%	84%	58%	71%	75%	60%
80.2%	87%	81%	74%	85%	81%	73%
66.3%	65%	79%	69%	68%	57%	60%
63.5%	64%	63%	47%	77%	73%	57%
84.8%	82%	90%	86%	80%	80%	91%
79.7%	82%	85%	71%	76%	81%	83%
81.5%	83%	86%	82%	83%	70%	85%
58.3%	64%	71%	56%	57%	53%	49%
84.5%	85%	87%	82%	88%	81%	84%
82.8%	85%	88%	75%	84%	82%	83%
65.0%	72%	72%	68%	69%	55%	54%
88.3%	88%	85%	90%	86%	89%	92%
88.0%	80%	93%	91%	92%	94%	78%
86.5%	89%	75%	90%	93%	93%	79%
73.5%	83%	83%	59%	71%	78%	67%
75.5%	85%	81%	66%	80%	62%	79%
83.5%	95%	81%	92%	94%	64%	75%
82.3%	81%	84%	81%	78%	84%	86%
73.3%	71%	81%	76%	67%	68%	77%
62.7%	76%	81%	60%	57%	44%	58%
67.7%	74%	72%	54%	76%	67%	63%
72.7%	82%	76%	56%	74%	72%	76%
79.5%	88%	79%	82%	80%	72%	76%
83.7%	91%	89%	88%	83%	67%	84%
86.3%	84%	81%	91%	89%	87%	86%
85.3%	88%	89%	75%	84%	85%	91%
73.8%	87%	66%	71%	86%	61%	72%